Facial Recognition Using Multisensor Images Based on Localized Kernel Eigen Spaces

• Published in: IEEE transactions on image processing Vol. 18; no. 6; pp. 1314 - 1325
• Main Authors: Gundimada, S., Asari, V.K.
• Format: Journal Article
• Language: English
• Published: New York, NY IEEE 01.06.2009; Institute of Electrical and Electronics Engineers; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Algorithms; Applied sciences; Artificial Intelligence; Biometrics; Data mining; Detection, estimation, filtering, equalization, prediction; Exact sciences and technology; Face; Face recognition; Facial; Feature extraction; Feature recognition; Humans; Image databases; image fusion; Image processing; Image Processing, Computer-Assisted - methods; Image recognition; Information theory; Information, signal and communications theory; Kernel; kernel methods; Kernels; Lighting; Modular; Pattern recognition; Pattern Recognition, Automated - methods; phase congruency; Photography; Principal Component Analysis - methods; Recognition; ROC Curve; Signal and communications theory; Signal processing; Signal, noise; Spatial databases; Studies; Telecommunications and information theory; Temperature; Thermography; Visual; Visual databases; Biometrics; Performance evaluation; Information integration; Phase measurement; Image recognition; Image processing; Temperature effect; Implementation; Partial occlusion; Learning; Accuracy; Database; Localization; Multisensor; Face recognition; phase congruency; Pattern recognition; Kernel method; Thermal image; Information processing; Signal processing; kernel methods; Feature extraction; Data fusion; Thermal imaging; Automatic recognition; Image fusion
• ISSN: 1057-7149; 1941-0042
• DOI: 10.1109/TIP.2009.2016713

A feature selection technique along with an information fusion procedure for improving the recognition accuracy of a visual and thermal image-based facial recognition system is presented in this paper. A novel modular kernel eigenspaces approach is developed and implemented on the phase congruency feature maps extracted from the visual and thermal images individually. Smaller sub-regions from a predefined neighborhood within the phase congruency images of the training samples are merged to obtain a large set of features. These features are then projected into higher dimensional spaces using kernel methods. The proposed localized nonlinear feature selection procedure helps to overcome the bottlenecks of illumination variations, partial occlusions, expression variations and variations due to temperature changes that affect the visual and thermal face recognition techniques. AR and Equinox databases are used for experimentation and evaluation of the proposed technique. The proposed feature selection procedure has greatly improved the recognition accuracy for both the visual and thermal images when compared to conventional techniques. Also, a decision level fusion methodology is presented which along with the feature selection procedure has outperformed various other face recognition techniques in terms of recognition accuracy.